# Learning to Learn Morphological Inflection for Resource-Poor Languages

arXiv: https://arxiv.org/abs/2004.13304 · HTML: https://mlsanity.com/paper/2004.13304/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 3 of 3)

- [Meta-Learning for Fast Cross-Lingual Adaptation in Dependency Parsing](https://mlsanity.com/paper/2104.04736/) (2021)
- [Minimal Supervision for Morphological Inflection](https://mlsanity.com/paper/2104.08512/) (2021)
- [Optimized Tokenization for Transcribed Error Correction](https://mlsanity.com/paper/2310.10704/) (2023)

## Abstract (arXiv)

We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource source languages to learn a set of model parameters that can serve as a strong initialization point for fine-tuning on a resource-poor target language. Experiments with two model architectures on 29 target languages from 3 families show that our suggested approach outperforms all baselines. In particular, it obtains a 31.7% higher absolute accuracy than a previously proposed cross-lingual transfer model and outperforms the previous state of the art by 1.7% absolute accuracy on average over languages.